trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 209,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 691.5,
      "epoch": 0.004784688995215311,
      "grad_norm": 0.16871348023414612,
      "kl": 0.0,
      "learning_rate": 2.3809523809523811e-07,
      "loss": -0.0,
      "reward": -0.1928749978542328,
      "reward_std": 0.5455328822135925,
      "rewards/correctness_reward_func": 0.0,
      "rewards/int_reward_func": 0.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.1928749978542328,
      "step": 1
    }
],
"logging_steps": 1,
"max_steps": 1,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
  "TrainerControl": {
    "args": {
      "should_epoch_stop": false,
      "should_evaluate": false,
      "should_log": false,
      "should_save": true,
      "should_training_stop": true
    },
    "attributes": {}
  }
},
"total_flos": 0.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}